Metagame Autobalancing for Competitive Multiplayer Games

Automated game balancing has often focused on single-agent scenarios. In this paper we present a tool for balancing multi-player games during game design. Our approach requires a designer to construct an intuitive graphical representation of their meta-game target, representing the relative scores that high-level strategies (or decks, or character types) should experience. This permits more sophisticated balance targets to be defined beyond a simple requirement of equal win chances. We then find a parameterization of the game that meets this target using simulation-based optimization to minimize the distance to the target graph. We show the capabilities of this tool on examples inheriting from Rock-Paper-Scissors, and on a more complex asymmetric fighting game.

[1]  Xuelong Li,et al.  A survey of graph edit distance , 2010, Pattern Analysis and Applications.

[2]  Mitchell Harrop,et al.  Metagames, paragames and orthogames: a new vocabulary , 2012, FDG.

[3]  Yoshua Bengio,et al.  Algorithms for Hyper-Parameter Optimization , 2011, NIPS.

[4]  Steve Marschner,et al.  Balancing Zero-Sum Games with One Variable per Strategy , 2017, AIIDE.

[5]  Mark J. Nelson.  Game Metrics Without Players: Strategies for Understanding Game Artifacts , 2011, Artificial Intelligence in the Game Design Process.

[6]  Simon M. Lucas,et al.  A Survey of Monte Carlo Tree Search Methods , 2012, IEEE Transactions on Computational Intelligence and AI in Games.

[7]  Sam Devlin,et al.  A Generalized Framework for Self-Play Training , 2019, 2019 IEEE Conference on Games (CoG).

[8]  James R. Lee,et al.  Understanding Game Balance with Quantitative Methods , 2013 .

[9]  Michael P. Wellman.  Methods for Empirical Game-Theoretic Analysis , 2006, AAAI.

[10]  Mike Preuss,et al.  An integrated process for game balancing , 2016, 2016 IEEE Conference on Computational Intelligence and Games (CIG).

[11]  Supervised learning as a tool for metagame analysis , 2014 .

[12]  Takuya Akiba,et al.  Optuna: A Next-generation Hyperparameter Optimization Framework , 2019, KDD.

[13]  Julian Togelius,et al.  Procedural Content Generation in Games , 2016, Computational Synthesis and Creative Systems.

[14]  Choong-Soo Lee,et al.  Investigating the Impact of Game Features on Champion Usage in League of Legends , 2015, FDG.

[15]  Pier Luca Lanzi.  Evaluating the Complexity of Players’ Strategies using MCTS Iterations , 2019, 2019 IEEE Conference on Games (CoG).

[16]  Mark O. Riedl,et al.  Monte-Carlo Tree Search for Simulation-based Play Strategy Analysis , 2015, FDG.

[17]  Karl Tuyls,et al.  alpha-Rank: Multi-Agent Evaluation by Evolution , 2019 .

[18]  Max Jaderberg,et al.  Open-ended Learning in Symmetric Zero-sum Games , 2019, ICML.

[19]  Sushil J. Louis,et al.  Using coevolution to understand and validate game balance in continuous games , 2008, GECCO '08.

[20]  Wojciech Zaremba,et al.  OpenAI Gym , 2016, ArXiv.

[21]  Julian Togelius,et al.  Artificial Intelligence and Games , 2018, Springer International Publishing.

[22]  Riccardo Poli,et al.  Evolving a designer-balanced neural network for Ms PacMan , 2017, 2017 9th Computer Science and Electronic Engineering (CEEC).